plopslop

technology

rss
newest firstBack to technology

Optimizing Jagged Flash Attention with TLX: The Road Toward SOTA FA4 on Blackwell

PyTorch11d ago

Featured projects TL;DR In this blog post, we present our work on Jagged Flash Attention (JFA) — the attention kernel behind Meta’s Generative Ads Model (GEM) — on NVIDIA Blackwell (B200), built...